Initial commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- added_tokens.json +13 -0
- logs.txt +300 -0
- mlc-chat-config.json +87 -0
- ndarray-cache-b16.json +0 -0
- ndarray-cache.json +0 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_100.bin +3 -0
- params_shard_101.bin +3 -0
- params_shard_102.bin +3 -0
- params_shard_103.bin +3 -0
- params_shard_104.bin +3 -0
- params_shard_105.bin +3 -0
- params_shard_106.bin +3 -0
- params_shard_107.bin +3 -0
- params_shard_108.bin +3 -0
- params_shard_109.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_110.bin +3 -0
- params_shard_111.bin +3 -0
- params_shard_112.bin +3 -0
- params_shard_113.bin +3 -0
- params_shard_114.bin +3 -0
- params_shard_115.bin +3 -0
- params_shard_116.bin +3 -0
- params_shard_117.bin +3 -0
- params_shard_118.bin +3 -0
- params_shard_119.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_120.bin +3 -0
- params_shard_121.bin +3 -0
- params_shard_122.bin +3 -0
- params_shard_123.bin +3 -0
- params_shard_124.bin +3 -0
- params_shard_125.bin +3 -0
- params_shard_126.bin +3 -0
- params_shard_127.bin +3 -0
- params_shard_128.bin +3 -0
- params_shard_129.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 32000,
|
3 |
+
"<|assistant|>": 32001,
|
4 |
+
"<|placeholder1|>": 32002,
|
5 |
+
"<|placeholder2|>": 32003,
|
6 |
+
"<|placeholder3|>": 32004,
|
7 |
+
"<|placeholder4|>": 32005,
|
8 |
+
"<|system|>": 32006,
|
9 |
+
"<|end|>": 32007,
|
10 |
+
"<|placeholder5|>": 32008,
|
11 |
+
"<|placeholder6|>": 32009,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
logs.txt
ADDED
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
0 |
0%| | 0/195 [00:00<?, ?it/s]
|
1 |
|
|
|
2 |
0%| | 0/195 [00:00<?, ?it/s]
|
3 |
|
|
|
4 |
0%| | 0/195 [00:06<?, ?it/s]/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
|
|
|
|
|
|
|
|
|
5 |
1%| | 1/195 [00:08<26:16, 8.13s/it]
|
6 |
|
|
|
7 |
1%| | 1/195 [00:08<26:16, 8.13s/it]
|
8 |
|
|
|
9 |
1%| | 1/195 [00:08<26:16, 8.13s/it]
|
10 |
2%|▏ | 3/195 [00:08<07:05, 2.22s/it]
|
11 |
|
|
|
12 |
2%|▏ | 3/195 [00:08<07:05, 2.22s/it]
|
13 |
2%|▏ | 4/195 [00:08<05:13, 1.64s/it]
|
14 |
|
|
|
15 |
2%|▏ | 4/195 [00:08<05:13, 1.64s/it]
|
16 |
|
|
|
17 |
2%|▏ | 4/195 [00:09<05:13, 1.64s/it]
|
18 |
3%|▎ | 6/195 [00:09<02:50, 1.11it/s]
|
19 |
|
|
|
20 |
3%|▎ | 6/195 [00:09<02:50, 1.11it/s]
|
21 |
|
|
|
22 |
3%|▎ | 6/195 [00:09<02:50, 1.11it/s]
|
23 |
4%|▍ | 8/195 [00:09<01:49, 1.71it/s]
|
24 |
|
|
|
25 |
4%|▍ | 8/195 [00:09<01:49, 1.71it/s]
|
26 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
27 |
|
|
|
28 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
29 |
|
|
|
30 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
31 |
|
|
|
32 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
33 |
6%|▌ | 12/195 [00:10<01:05, 2.79it/s]
|
34 |
|
|
|
35 |
6%|▌ | 12/195 [00:10<01:05, 2.79it/s]
|
36 |
|
|
|
37 |
6%|▌ | 12/195 [00:10<01:05, 2.79it/s]
|
38 |
7%|▋ | 14/195 [00:10<00:52, 3.46it/s]
|
39 |
|
|
|
40 |
7%|▋ | 14/195 [00:10<00:52, 3.46it/s]
|
41 |
8%|▊ | 15/195 [00:11<01:00, 2.98it/s]
|
42 |
|
|
|
43 |
8%|▊ | 15/195 [00:11<01:00, 2.98it/s]
|
44 |
|
|
|
45 |
8%|▊ | 15/195 [00:11<01:00, 2.98it/s]
|
46 |
9%|▊ | 17/195 [00:11<00:42, 4.19it/s]
|
47 |
|
|
|
48 |
9%|▊ | 17/195 [00:11<00:42, 4.19it/s]
|
49 |
9%|▉ | 18/195 [00:11<00:45, 3.93it/s]
|
50 |
|
|
|
51 |
9%|▉ | 18/195 [00:11<00:45, 3.93it/s]
|
52 |
|
|
|
53 |
9%|▉ | 18/195 [00:11<00:45, 3.93it/s]
|
54 |
10%|█ | 20/195 [00:12<00:37, 4.70it/s]
|
55 |
|
|
|
56 |
10%|█ | 20/195 [00:12<00:37, 4.70it/s]
|
57 |
11%|█ | 21/195 [00:12<00:48, 3.56it/s]
|
58 |
|
|
|
59 |
11%|█ | 21/195 [00:12<00:48, 3.56it/s]
|
60 |
|
|
|
61 |
11%|█ | 21/195 [00:12<00:48, 3.56it/s]
|
62 |
12%|█▏ | 23/195 [00:12<00:33, 5.06it/s]
|
63 |
|
|
|
64 |
12%|█▏ | 23/195 [00:12<00:33, 5.06it/s]
|
65 |
12%|█▏ | 24/195 [00:13<00:37, 4.54it/s]
|
66 |
|
|
|
67 |
12%|█▏ | 24/195 [00:13<00:37, 4.54it/s]
|
68 |
|
|
|
69 |
12%|█▏ | 24/195 [00:13<00:37, 4.54it/s]
|
70 |
13%|█▎ | 26/195 [00:13<00:32, 5.27it/s]
|
71 |
|
|
|
72 |
13%|█▎ | 26/195 [00:13<00:32, 5.27it/s]
|
73 |
14%|█▍ | 27/195 [00:13<00:44, 3.78it/s]
|
74 |
|
|
|
75 |
14%|█▍ | 27/195 [00:13<00:44, 3.78it/s]
|
76 |
|
|
|
77 |
14%|█▍ | 27/195 [00:13<00:44, 3.78it/s]
|
78 |
15%|█▍ | 29/195 [00:13<00:30, 5.37it/s]
|
79 |
|
|
|
80 |
15%|█▍ | 29/195 [00:13<00:30, 5.37it/s]
|
81 |
15%|█▌ | 30/195 [00:14<00:35, 4.71it/s]
|
82 |
|
|
|
83 |
15%|█▌ | 30/195 [00:14<00:35, 4.71it/s]
|
84 |
|
|
|
85 |
15%|█▌ | 30/195 [00:14<00:35, 4.71it/s]
|
86 |
16%|█▋ | 32/195 [00:14<00:30, 5.39it/s]
|
87 |
|
|
|
88 |
16%|█▋ | 32/195 [00:14<00:30, 5.39it/s]
|
89 |
17%|█▋ | 33/195 [00:15<00:42, 3.82it/s]
|
90 |
|
|
|
91 |
17%|█▋ | 33/195 [00:15<00:42, 3.82it/s]
|
92 |
|
|
|
93 |
17%|█▋ | 33/195 [00:15<00:42, 3.82it/s]
|
94 |
18%|█▊ | 35/195 [00:15<00:29, 5.44it/s]
|
95 |
|
|
|
96 |
18%|█▊ | 35/195 [00:15<00:29, 5.44it/s]
|
97 |
18%|█▊ | 36/195 [00:15<00:33, 4.76it/s]
|
98 |
|
|
|
99 |
18%|█▊ | 36/195 [00:15<00:33, 4.76it/s]
|
100 |
|
|
|
101 |
18%|█▊ | 36/195 [00:15<00:33, 4.76it/s]
|
102 |
19%|█▉ | 38/195 [00:15<00:28, 5.45it/s]
|
103 |
|
|
|
104 |
19%|█▉ | 38/195 [00:15<00:28, 5.45it/s]
|
105 |
20%|██ | 39/195 [00:16<00:40, 3.85it/s]
|
106 |
|
|
|
107 |
20%|██ | 39/195 [00:16<00:40, 3.85it/s]
|
108 |
|
|
|
109 |
20%|██ | 39/195 [00:16<00:40, 3.85it/s]
|
110 |
21%|██ | 41/195 [00:16<00:28, 5.48it/s]
|
111 |
|
|
|
112 |
21%|██ | 41/195 [00:16<00:28, 5.48it/s]
|
113 |
22%|██▏ | 42/195 [00:16<00:32, 4.75it/s]
|
114 |
|
|
|
115 |
22%|██▏ | 42/195 [00:16<00:32, 4.75it/s]
|
116 |
|
|
|
117 |
22%|██▏ | 42/195 [00:16<00:32, 4.75it/s]
|
118 |
23%|██▎ | 44/195 [00:17<00:27, 5.43it/s]
|
119 |
|
|
|
120 |
23%|██▎ | 44/195 [00:17<00:27, 5.43it/s]
|
121 |
23%|██▎ | 45/195 [00:17<00:39, 3.83it/s]
|
122 |
|
|
|
123 |
23%|██▎ | 45/195 [00:17<00:39, 3.83it/s]
|
124 |
|
|
|
125 |
23%|██▎ | 45/195 [00:17<00:39, 3.83it/s]
|
126 |
24%|██▍ | 47/195 [00:17<00:27, 5.44it/s]
|
127 |
|
|
|
128 |
24%|██▍ | 47/195 [00:17<00:27, 5.44it/s]
|
129 |
25%|██▍ | 48/195 [00:18<00:30, 4.75it/s]
|
130 |
|
|
|
131 |
25%|██▍ | 48/195 [00:18<00:30, 4.75it/s]
|
132 |
|
|
|
133 |
25%|██▍ | 48/195 [00:18<00:30, 4.75it/s]
|
134 |
26%|██▌ | 50/195 [00:18<00:26, 5.43it/s]
|
135 |
|
|
|
136 |
26%|██▌ | 50/195 [00:18<00:26, 5.43it/s]
|
137 |
26%|██▌ | 51/195 [00:18<00:37, 3.82it/s]
|
138 |
|
|
|
139 |
26%|██▌ | 51/195 [00:18<00:37, 3.82it/s]
|
140 |
|
|
|
141 |
26%|██▌ | 51/195 [00:18<00:37, 3.82it/s]
|
142 |
27%|██▋ | 53/195 [00:18<00:26, 5.44it/s]
|
143 |
|
|
|
144 |
27%|██▋ | 53/195 [00:18<00:26, 5.44it/s]
|
145 |
28%|██▊ | 54/195 [00:19<00:29, 4.74it/s]
|
146 |
|
|
|
147 |
28%|██▊ | 54/195 [00:19<00:29, 4.74it/s]
|
148 |
|
|
|
149 |
28%|██▊ | 54/195 [00:19<00:29, 4.74it/s]
|
150 |
29%|██▊ | 56/195 [00:19<00:25, 5.38it/s]
|
151 |
|
|
|
152 |
29%|██▊ | 56/195 [00:19<00:25, 5.38it/s]
|
153 |
29%|██▉ | 57/195 [00:20<00:36, 3.80it/s]
|
154 |
|
|
|
155 |
29%|██▉ | 57/195 [00:20<00:36, 3.80it/s]
|
156 |
|
|
|
157 |
29%|██▉ | 57/195 [00:20<00:36, 3.80it/s]
|
158 |
30%|███ | 59/195 [00:20<00:25, 5.41it/s]
|
159 |
|
|
|
160 |
30%|███ | 59/195 [00:20<00:25, 5.41it/s]
|
161 |
31%|███ | 60/195 [00:20<00:28, 4.73it/s]
|
162 |
|
|
|
163 |
31%|███ | 60/195 [00:20<00:28, 4.73it/s]
|
164 |
|
|
|
165 |
31%|███ | 60/195 [00:20<00:28, 4.73it/s]
|
166 |
32%|███▏ | 62/195 [00:20<00:24, 5.41it/s]
|
167 |
|
|
|
168 |
32%|███▏ | 62/195 [00:20<00:24, 5.41it/s]
|
169 |
32%|███▏ | 63/195 [00:21<00:34, 3.82it/s]
|
170 |
|
|
|
171 |
32%|███▏ | 63/195 [00:21<00:34, 3.82it/s]
|
172 |
|
|
|
173 |
32%|███▏ | 63/195 [00:21<00:34, 3.82it/s]
|
174 |
33%|███▎ | 65/195 [00:21<00:23, 5.44it/s]
|
175 |
|
|
|
176 |
33%|███▎ | 65/195 [00:21<00:23, 5.44it/s]
|
177 |
34%|███▍ | 66/195 [00:21<00:27, 4.74it/s]
|
178 |
|
|
|
179 |
34%|███▍ | 66/195 [00:21<00:27, 4.74it/s]
|
180 |
|
|
|
181 |
34%|███▍ | 66/195 [00:21<00:27, 4.74it/s]
|
182 |
|
|
|
183 |
34%|███▍ | 66/195 [00:22<00:27, 4.74it/s]
|
184 |
|
|
|
185 |
34%|███▍ | 66/195 [00:32<00:27, 4.74it/s]
|
186 |
35%|███▍ | 68/195 [00:33<04:46, 2.25s/it]
|
187 |
|
|
|
188 |
35%|███▍ | 68/195 [00:33<04:46, 2.25s/it]
|
189 |
|
|
|
190 |
35%|███▍ | 68/195 [00:33<04:46, 2.25s/it]
|
191 |
36%|███▌ | 70/195 [00:33<03:09, 1.52s/it]
|
192 |
|
|
|
193 |
36%|███▌ | 70/195 [00:33<03:09, 1.52s/it]
|
194 |
36%|███▋ | 71/195 [00:33<02:43, 1.32s/it]
|
195 |
|
|
|
196 |
36%|███▋ | 71/195 [00:33<02:43, 1.32s/it]
|
197 |
|
|
|
198 |
36%|███▋ | 71/195 [00:33<02:43, 1.32s/it]
|
199 |
37%|███▋ | 73/195 [00:33<01:44, 1.16it/s]
|
200 |
|
|
|
201 |
37%|███▋ | 73/195 [00:33<01:44, 1.16it/s]
|
202 |
38%|███▊ | 74/195 [00:34<01:30, 1.34it/s]
|
203 |
|
|
|
204 |
38%|███▊ | 74/195 [00:34<01:30, 1.34it/s]
|
205 |
|
|
|
206 |
38%|███▊ | 74/195 [00:34<01:30, 1.34it/s]
|
207 |
39%|███▉ | 76/195 [00:34<01:01, 1.92it/s]
|
208 |
|
|
|
209 |
39%|███▉ | 76/195 [00:34<01:01, 1.92it/s]
|
210 |
39%|███▉ | 77/195 [00:35<01:01, 1.91it/s]
|
211 |
|
|
|
212 |
39%|███▉ | 77/195 [00:35<01:01, 1.91it/s]
|
213 |
|
|
|
214 |
39%|███▉ | 77/195 [00:35<01:01, 1.91it/s]
|
215 |
41%|████ | 79/195 [00:35<00:40, 2.87it/s]
|
216 |
|
|
|
217 |
41%|████ | 79/195 [00:35<00:40, 2.87it/s]
|
218 |
41%|████ | 80/195 [00:35<00:38, 2.95it/s]
|
219 |
|
|
|
220 |
41%|████ | 80/195 [00:35<00:38, 2.95it/s]
|
221 |
|
|
|
222 |
41%|████ | 80/195 [00:35<00:38, 2.95it/s]
|
223 |
42%|████▏ | 82/195 [00:35<00:29, 3.80it/s]
|
224 |
|
|
|
225 |
42%|████▏ | 82/195 [00:35<00:29, 3.80it/s]
|
226 |
43%|████▎ | 83/195 [00:36<00:35, 3.12it/s]
|
227 |
|
|
|
228 |
43%|████▎ | 83/195 [00:36<00:35, 3.12it/s]
|
229 |
|
|
|
230 |
43%|████▎ | 83/195 [00:36<00:35, 3.12it/s]
|
231 |
44%|████▎ | 85/195 [00:36<00:24, 4.53it/s]
|
232 |
|
|
|
233 |
44%|████▎ | 85/195 [00:36<00:24, 4.53it/s]
|
234 |
44%|████▍ | 86/195 [00:36<00:25, 4.20it/s]
|
235 |
|
|
|
236 |
44%|████▍ | 86/195 [00:36<00:25, 4.20it/s]
|
237 |
|
|
|
238 |
44%|████▍ | 86/195 [00:36<00:25, 4.20it/s]
|
239 |
45%|████▌ | 88/195 [00:36<00:21, 4.99it/s]
|
240 |
|
|
|
241 |
45%|████▌ | 88/195 [00:37<00:21, 4.99it/s]
|
242 |
46%|████▌ | 89/195 [00:37<00:28, 3.68it/s]
|
243 |
|
|
|
244 |
46%|████▌ | 89/195 [00:37<00:28, 3.68it/s]
|
245 |
|
|
|
246 |
46%|████▌ | 89/195 [00:37<00:28, 3.68it/s]
|
247 |
47%|████▋ | 91/195 [00:37<00:19, 5.25it/s]
|
248 |
|
|
|
249 |
47%|████▋ | 91/195 [00:37<00:19, 5.25it/s]
|
250 |
47%|████▋ | 92/195 [00:37<00:22, 4.67it/s]
|
251 |
|
|
|
252 |
47%|████▋ | 92/195 [00:37<00:22, 4.67it/s]
|
253 |
|
|
|
254 |
47%|████▋ | 92/195 [00:37<00:22, 4.67it/s]
|
255 |
48%|████▊ | 94/195 [00:38<00:18, 5.40it/s]
|
256 |
|
|
|
257 |
48%|████▊ | 94/195 [00:38<00:18, 5.40it/s]
|
258 |
49%|████▊ | 95/195 [00:38<00:25, 3.85it/s]
|
259 |
|
|
|
260 |
49%|████▊ | 95/195 [00:38<00:25, 3.85it/s]
|
261 |
|
|
|
262 |
49%|████▊ | 95/195 [00:38<00:25, 3.85it/s]
|
263 |
50%|████▉ | 97/195 [00:38<00:17, 5.48it/s]
|
264 |
|
|
|
265 |
50%|████▉ | 97/195 [00:38<00:17, 5.48it/s]
|
266 |
50%|█████ | 98/195 [00:39<00:20, 4.81it/s]
|
267 |
|
|
|
268 |
50%|█████ | 98/195 [00:39<00:20, 4.81it/s]
|
269 |
|
|
|
270 |
50%|█████ | 98/195 [00:39<00:20, 4.81it/s]
|
271 |
51%|█████▏ | 100/195 [00:39<00:17, 5.50it/s]
|
272 |
|
|
|
273 |
51%|█████▏ | 100/195 [00:39<00:17, 5.50it/s]
|
274 |
52%|█████▏ | 101/195 [00:39<00:24, 3.90it/s]
|
275 |
|
|
|
276 |
52%|█████▏ | 101/195 [00:39<00:24, 3.90it/s]
|
277 |
|
|
|
278 |
52%|█████▏ | 101/195 [00:39<00:24, 3.90it/s]
|
279 |
53%|█████▎ | 103/195 [00:40<00:16, 5.53it/s]
|
280 |
|
|
|
281 |
53%|█████▎ | 103/195 [00:40<00:16, 5.53it/s]
|
282 |
53%|█████▎ | 104/195 [00:40<00:18, 4.84it/s]
|
283 |
|
|
|
284 |
53%|█████▎ | 104/195 [00:40<00:18, 4.84it/s]
|
285 |
|
|
|
286 |
53%|█████▎ | 104/195 [00:40<00:18, 4.84it/s]
|
287 |
54%|█████▍ | 106/195 [00:40<00:16, 5.53it/s]
|
288 |
|
|
|
289 |
54%|█████▍ | 106/195 [00:40<00:16, 5.53it/s]
|
290 |
55%|█████▍ | 107/195 [00:41<00:22, 3.91it/s]
|
291 |
|
|
|
292 |
55%|█████▍ | 107/195 [00:41<00:22, 3.91it/s]
|
293 |
|
|
|
294 |
55%|█████▍ | 107/195 [00:41<00:22, 3.91it/s]
|
295 |
56%|█████▌ | 109/195 [00:41<00:15, 5.55it/s]
|
296 |
|
|
|
297 |
56%|█████▌ | 109/195 [00:41<00:15, 5.55it/s]
|
298 |
56%|█████▋ | 110/195 [00:41<00:17, 4.84it/s]
|
299 |
|
|
|
300 |
56%|█████▋ | 110/195 [00:41<00:17, 4.84it/s]
|
301 |
|
|
|
302 |
56%|█████▋ | 110/195 [00:41<00:17, 4.84it/s]
|
303 |
57%|█████▋ | 112/195 [00:41<00:15, 5.53it/s]
|
304 |
|
|
|
305 |
57%|█████▋ | 112/195 [00:41<00:15, 5.53it/s]
|
306 |
58%|█████▊ | 113/195 [00:42<00:20, 3.91it/s]
|
307 |
|
|
|
308 |
58%|█████▊ | 113/195 [00:42<00:20, 3.91it/s]
|
309 |
|
|
|
310 |
58%|█████▊ | 113/195 [00:42<00:20, 3.91it/s]
|
311 |
59%|█████▉ | 115/195 [00:42<00:14, 5.55it/s]
|
312 |
|
|
|
313 |
59%|█████▉ | 115/195 [00:42<00:14, 5.55it/s]
|
314 |
59%|█████▉ | 116/195 [00:42<00:16, 4.84it/s]
|
315 |
|
|
|
316 |
59%|█████▉ | 116/195 [00:42<00:16, 4.84it/s]
|
317 |
|
|
|
318 |
59%|█████▉ | 116/195 [00:42<00:16, 4.84it/s]
|
319 |
61%|██████ | 118/195 [00:43<00:13, 5.51it/s]
|
320 |
|
|
|
321 |
61%|██████ | 118/195 [00:43<00:13, 5.51it/s]
|
322 |
61%|██████ | 119/195 [00:43<00:19, 3.89it/s]
|
323 |
|
|
|
324 |
61%|██████ | 119/195 [00:43<00:19, 3.89it/s]
|
325 |
|
|
|
326 |
61%|██████ | 119/195 [00:43<00:19, 3.89it/s]
|
327 |
62%|██████▏ | 121/195 [00:43<00:13, 5.53it/s]
|
328 |
|
|
|
329 |
62%|██████▏ | 121/195 [00:43<00:13, 5.53it/s]
|
330 |
63%|██████▎ | 122/195 [00:44<00:15, 4.83it/s]
|
331 |
|
|
|
332 |
63%|██████▎ | 122/195 [00:44<00:15, 4.83it/s]
|
333 |
|
|
|
334 |
63%|██████▎ | 122/195 [00:44<00:15, 4.83it/s]
|
335 |
64%|██████▎ | 124/195 [00:44<00:12, 5.53it/s]
|
336 |
|
|
|
337 |
64%|██████▎ | 124/195 [00:44<00:12, 5.53it/s]
|
338 |
64%|██████▍ | 125/195 [00:44<00:17, 3.91it/s]
|
339 |
|
|
|
340 |
64%|██████▍ | 125/195 [00:44<00:17, 3.91it/s]
|
341 |
|
|
|
342 |
64%|██████▍ | 125/195 [00:44<00:17, 3.91it/s]
|
343 |
65%|██████▌ | 127/195 [00:44<00:12, 5.54it/s]
|
344 |
|
|
|
345 |
65%|██████▌ | 127/195 [00:45<00:12, 5.54it/s]
|
346 |
66%|██████▌ | 128/195 [00:45<00:13, 4.82it/s]
|
347 |
|
|
|
348 |
66%|██████▌ | 128/195 [00:45<00:13, 4.82it/s]
|
349 |
|
|
|
350 |
66%|██████▌ | 128/195 [00:45<00:13, 4.82it/s]
|
351 |
67%|██████▋ | 130/195 [00:45<00:11, 5.51it/s]
|
352 |
|
|
|
353 |
67%|██████▋ | 130/195 [00:45<00:11, 5.51it/s]
|
354 |
67%|██████▋ | 131/195 [00:46<00:16, 3.91it/s]
|
355 |
|
|
|
356 |
67%|██████▋ | 131/195 [00:46<00:16, 3.91it/s]
|
357 |
|
|
|
358 |
67%|██████▋ | 131/195 [00:46<00:16, 3.91it/s]
|
359 |
68%|██████▊ | 133/195 [00:46<00:11, 5.55it/s]
|
360 |
|
|
|
361 |
68%|██████▊ | 133/195 [00:46<00:11, 5.55it/s]
|
362 |
69%|██████▊ | 134/195 [00:46<00:12, 4.85it/s]
|
363 |
|
|
|
364 |
69%|██████▊ | 134/195 [00:46<00:12, 4.85it/s]
|
365 |
|
|
|
366 |
69%|██████▊ | 134/195 [00:46<00:12, 4.85it/s]
|
367 |
70%|██████▉ | 136/195 [00:46<00:10, 5.53it/s]
|
368 |
|
|
|
369 |
70%|██████▉ | 136/195 [00:46<00:10, 5.53it/s]
|
370 |
70%|███████ | 137/195 [00:47<00:14, 3.92it/s]
|
371 |
|
|
|
372 |
70%|███████ | 137/195 [00:47<00:14, 3.92it/s]
|
373 |
|
|
|
374 |
70%|███████ | 137/195 [00:47<00:14, 3.92it/s]
|
375 |
71%|███████▏ | 139/195 [00:47<00:10, 5.56it/s]
|
376 |
|
|
|
377 |
71%|███████▏ | 139/195 [00:47<00:10, 5.56it/s]
|
378 |
72%|███████▏ | 140/195 [00:47<00:11, 4.85it/s]
|
379 |
|
|
|
380 |
72%|███████▏ | 140/195 [00:47<00:11, 4.85it/s]
|
381 |
|
|
|
382 |
72%|███████▏ | 140/195 [00:47<00:11, 4.85it/s]
|
383 |
73%|███████▎ | 142/195 [00:48<00:09, 5.54it/s]
|
384 |
|
|
|
385 |
73%|███████▎ | 142/195 [00:48<00:09, 5.54it/s]
|
386 |
73%|███████▎ | 143/195 [00:48<00:13, 3.92it/s]
|
387 |
|
|
|
388 |
73%|███████▎ | 143/195 [00:48<00:13, 3.92it/s]
|
389 |
|
|
|
390 |
73%|███████▎ | 143/195 [00:48<00:13, 3.92it/s]
|
391 |
74%|███████▍ | 145/195 [00:48<00:09, 5.55it/s]
|
392 |
|
|
|
393 |
74%|███████▍ | 145/195 [00:48<00:09, 5.55it/s]
|
394 |
75%|███████▍ | 146/195 [00:48<00:10, 4.84it/s]
|
395 |
|
|
|
396 |
75%|███████▍ | 146/195 [00:48<00:10, 4.84it/s]
|
397 |
|
|
|
398 |
75%|███████▍ | 146/195 [00:48<00:10, 4.84it/s]
|
399 |
76%|███████▌ | 148/195 [00:49<00:08, 5.51it/s]
|
400 |
|
|
|
401 |
76%|███████▌ | 148/195 [00:49<00:08, 5.51it/s]
|
402 |
76%|███████▋ | 149/195 [00:49<00:11, 3.88it/s]
|
403 |
|
|
|
404 |
76%|███████▋ | 149/195 [00:49<00:11, 3.88it/s]
|
405 |
|
|
|
406 |
76%|███████▋ | 149/195 [00:49<00:11, 3.88it/s]
|
407 |
77%|███████▋ | 151/195 [00:49<00:07, 5.51it/s]
|
408 |
|
|
|
409 |
77%|███████▋ | 151/195 [00:49<00:07, 5.51it/s]
|
410 |
78%|███████▊ | 152/195 [00:50<00:08, 4.82it/s]
|
411 |
|
|
|
412 |
78%|███████▊ | 152/195 [00:50<00:08, 4.82it/s]
|
413 |
78%|███████▊ | 153/195 [00:50<00:07, 5.45it/s]
|
414 |
|
|
|
415 |
78%|███████▊ | 153/195 [00:50<00:07, 5.45it/s]
|
416 |
|
|
|
417 |
78%|███████▊ | 153/195 [00:50<00:07, 5.45it/s]
|
418 |
79%|███████▉ | 155/195 [00:50<00:06, 6.01it/s]
|
419 |
|
|
|
420 |
79%|███████▉ | 155/195 [00:50<00:06, 6.01it/s]
|
421 |
80%|████████ | 156/195 [00:51<00:09, 4.02it/s]
|
422 |
|
|
|
423 |
80%|████████ | 156/195 [00:51<00:09, 4.02it/s]
|
424 |
|
|
|
425 |
80%|████████ | 156/195 [00:51<00:09, 4.02it/s]
|
426 |
81%|████████ | 158/195 [00:51<00:06, 5.75it/s]
|
427 |
|
|
|
428 |
81%|████████ | 158/195 [00:51<00:06, 5.75it/s]
|
429 |
82%|████████▏ | 159/195 [00:51<00:07, 4.95it/s]
|
430 |
|
|
|
431 |
82%|████████▏ | 159/195 [00:51<00:07, 4.95it/s]
|
432 |
|
|
|
433 |
82%|████████▏ | 159/195 [00:51<00:07, 4.95it/s]
|
434 |
83%|████████▎ | 161/195 [00:51<00:06, 5.60it/s]
|
435 |
|
|
|
436 |
83%|████████▎ | 161/195 [00:51<00:06, 5.60it/s]
|
437 |
83%|████████▎ | 162/195 [00:52<00:08, 3.89it/s]
|
438 |
|
|
|
439 |
83%|████████▎ | 162/195 [00:52<00:08, 3.89it/s]
|
440 |
|
|
|
441 |
83%|████████▎ | 162/195 [00:52<00:08, 3.89it/s]
|
442 |
84%|████████▍ | 164/195 [00:52<00:05, 5.54it/s]
|
443 |
|
|
|
444 |
84%|████████▍ | 164/195 [00:52<00:05, 5.54it/s]
|
445 |
85%|████████▍ | 165/195 [00:52<00:06, 4.83it/s]
|
446 |
|
|
|
447 |
85%|████████▍ | 165/195 [00:52<00:06, 4.83it/s]
|
448 |
|
|
|
449 |
85%|████████▍ | 165/195 [00:52<00:06, 4.83it/s]
|
450 |
86%|████████▌ | 167/195 [00:53<00:05, 5.43it/s]
|
451 |
|
|
|
452 |
86%|████████▌ | 167/195 [00:53<00:05, 5.43it/s]
|
453 |
86%|████████▌ | 168/195 [00:53<00:07, 3.85it/s]
|
454 |
|
|
|
455 |
86%|████████▌ | 168/195 [00:53<00:07, 3.85it/s]
|
456 |
|
|
|
457 |
86%|████████▌ | 168/195 [00:53<00:07, 3.85it/s]
|
458 |
87%|████████▋ | 170/195 [00:53<00:04, 5.47it/s]
|
459 |
|
|
|
460 |
87%|████████▋ | 170/195 [00:53<00:04, 5.47it/s]
|
461 |
88%|████████▊ | 171/195 [00:54<00:05, 4.80it/s]
|
462 |
|
|
|
463 |
88%|████████▊ | 171/195 [00:54<00:05, 4.80it/s]
|
464 |
|
|
|
465 |
88%|████████▊ | 171/195 [00:54<00:05, 4.80it/s]
|
466 |
89%|████████▊ | 173/195 [00:54<00:03, 5.51it/s]
|
467 |
|
|
|
468 |
89%|████████▊ | 173/195 [00:54<00:03, 5.51it/s]
|
469 |
89%|████████▉ | 174/195 [00:54<00:05, 3.92it/s]
|
470 |
|
|
|
471 |
89%|████████▉ | 174/195 [00:54<00:05, 3.92it/s]
|
472 |
|
|
|
473 |
89%|████████▉ | 174/195 [00:54<00:05, 3.92it/s]
|
474 |
90%|█████████ | 176/195 [00:54<00:03, 5.56it/s]
|
475 |
|
|
|
476 |
90%|█████████ | 176/195 [00:54<00:03, 5.56it/s]
|
477 |
91%|█████████ | 177/195 [00:55<00:03, 4.86it/s]
|
478 |
|
|
|
479 |
91%|█████████ | 177/195 [00:55<00:03, 4.86it/s]
|
480 |
|
|
|
481 |
91%|█████████ | 177/195 [00:55<00:03, 4.86it/s]
|
482 |
92%|█████████▏| 179/195 [00:55<00:02, 5.54it/s]
|
483 |
|
|
|
484 |
92%|█████████▏| 179/195 [00:55<00:02, 5.54it/s]
|
485 |
92%|█████████▏| 180/195 [00:56<00:03, 3.90it/s]
|
486 |
|
|
|
487 |
92%|█████████▏| 180/195 [00:56<00:03, 3.90it/s]
|
488 |
|
|
|
489 |
92%|█████████▏| 180/195 [00:56<00:03, 3.90it/s]
|
490 |
93%|█████████▎| 182/195 [00:56<00:02, 5.54it/s]
|
491 |
|
|
|
492 |
93%|█████████▎| 182/195 [00:56<00:02, 5.54it/s]
|
493 |
94%|█████████▍| 183/195 [00:56<00:02, 4.87it/s]
|
494 |
|
|
|
495 |
94%|█████████▍| 183/195 [00:56<00:02, 4.87it/s]
|
496 |
|
|
|
497 |
94%|█████████▍| 183/195 [00:56<00:02, 4.87it/s]
|
498 |
95%|█████████▍| 185/195 [00:56<00:01, 5.56it/s]
|
499 |
|
|
|
500 |
95%|█████████▍| 185/195 [00:56<00:01, 5.56it/s]
|
501 |
95%|█████████▌| 186/195 [00:57<00:02, 3.88it/s]
|
502 |
|
|
|
503 |
95%|█████████▌| 186/195 [00:57<00:02, 3.88it/s]
|
504 |
|
|
|
505 |
95%|█████████▌| 186/195 [00:57<00:02, 3.88it/s]
|
506 |
96%|█████████▋| 188/195 [00:57<00:01, 5.46it/s]
|
507 |
|
|
|
508 |
96%|█████████▋| 188/195 [00:57<00:01, 5.46it/s]
|
509 |
97%|█████████▋| 189/195 [00:57<00:01, 4.81it/s]
|
510 |
|
|
|
511 |
97%|█████████▋| 189/195 [00:57<00:01, 4.81it/s]
|
512 |
|
|
|
513 |
97%|��████████▋| 189/195 [00:57<00:01, 4.81it/s]
|
514 |
98%|█████████▊| 191/195 [00:57<00:00, 5.52it/s]
|
515 |
|
|
|
516 |
98%|█████████▊| 191/195 [00:58<00:00, 5.52it/s]
|
517 |
98%|█████████▊| 192/195 [00:58<00:00, 3.92it/s]
|
518 |
|
|
|
519 |
98%|█████████▊| 192/195 [00:58<00:00, 3.92it/s]
|
520 |
|
|
|
521 |
98%|█████████▊| 192/195 [00:58<00:00, 3.92it/s]
|
522 |
99%|█████████▉| 194/195 [00:58<00:00, 5.56it/s]
|
523 |
|
|
|
524 |
99%|█████████▉| 194/195 [00:58<00:00, 5.56it/s]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd1/rickzhou/models/Phi-3-mini-4k-instruct --quantization q0f32 --conv-template phi-3 --output /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC
|
2 |
+
[2024-05-27 02:07:22] INFO auto_config.py:115: [92mFound[0m model configuration: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/config.json
|
3 |
+
[2024-05-27 02:07:22] INFO auto_config.py:153: [92mFound[0m model type: [1mphi3[0m. Use `--model-type` to override.
|
4 |
+
[2024-05-27 02:07:22] INFO phi3_model.py:53: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
|
5 |
+
[2024-05-27 02:07:22] INFO phi3_model.py:68: [1mprefill_chunk_size[0m defaults to 2048
|
6 |
+
[2024-05-27 02:07:22] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80
|
7 |
+
[2024-05-27 02:07:22] INFO gen_config.py:142: [generation_config.json] Setting [1mbos_token_id[0m: 1
|
8 |
+
[2024-05-27 02:07:22] INFO gen_config.py:142: [generation_config.json] Setting [1meos_token_id[0m: [32000, 32001, 32007]
|
9 |
+
[2024-05-27 02:07:22] INFO gen_config.py:142: [generation_config.json] Setting [1mpad_token_id[0m: 32000
|
10 |
+
[2024-05-27 02:07:22] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/tokenizer.model. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/tokenizer.model[0m
|
11 |
+
[2024-05-27 02:07:22] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/tokenizer.json. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/tokenizer.json[0m
|
12 |
+
[2024-05-27 02:07:22] INFO gen_config.py:156: [91mNot found[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/vocab.json
|
13 |
+
[2024-05-27 02:07:22] INFO gen_config.py:156: [91mNot found[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/merges.txt
|
14 |
+
[2024-05-27 02:07:22] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/added_tokens.json. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/added_tokens.json[0m
|
15 |
+
[2024-05-27 02:07:22] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/tokenizer_config.json. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/tokenizer_config.json[0m
|
16 |
+
Traceback (most recent call last):
|
17 |
+
File "<frozen runpy>", line 198, in _run_module_as_main
|
18 |
+
File "<frozen runpy>", line 88, in _run_code
|
19 |
+
File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/__main__.py", line 52, in <module>
|
20 |
+
main()
|
21 |
+
File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/__main__.py", line 33, in main
|
22 |
+
cli.main(sys.argv[2:])
|
23 |
+
File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/cli/gen_config.py", line 95, in main
|
24 |
+
gen_config(
|
25 |
+
File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/interface/gen_config.py", line 214, in gen_config
|
26 |
+
mlc_chat_config.tokenizer_info = asdict(Tokenizer.detect_tokenizer_info(str(output)))
|
27 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
28 |
+
File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/tokenizer.py", line 114, in detect_tokenizer_info
|
29 |
+
return TokenizerInfo.from_json(_ffi_api.DetectTokenizerInfo(tokenizer_path)) # type: ignore # pylint: disable=no-member
|
30 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
31 |
+
AttributeError: module 'mlc_llm._ffi_api' has no attribute 'DetectTokenizerInfo'
|
32 |
+
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd1/rickzhou/models/Phi-3-mini-4k-instruct --quantization q0f32 --conv-template phi-3 --output /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC
|
33 |
+
[2024-05-27 03:04:28] INFO auto_config.py:115: [92mFound[0m model configuration: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/config.json
|
34 |
+
[2024-05-27 03:04:28] INFO auto_config.py:153: [92mFound[0m model type: [1mphi3[0m. Use `--model-type` to override.
|
35 |
+
[2024-05-27 03:04:28] INFO phi3_model.py:53: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
|
36 |
+
[2024-05-27 03:04:28] INFO phi3_model.py:68: [1mprefill_chunk_size[0m defaults to 2048
|
37 |
+
[2024-05-27 03:04:28] INFO config.py:106: Overriding [1mmax_batch_size[0m from 1 to 80
|
38 |
+
[2024-05-27 03:04:28] INFO gen_config.py:142: [generation_config.json] Setting [1mbos_token_id[0m: 1
|
39 |
+
[2024-05-27 03:04:28] INFO gen_config.py:142: [generation_config.json] Setting [1meos_token_id[0m: [32000, 32001, 32007]
|
40 |
+
[2024-05-27 03:04:28] INFO gen_config.py:142: [generation_config.json] Setting [1mpad_token_id[0m: 32000
|
41 |
+
[2024-05-27 03:04:28] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/tokenizer.model. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/tokenizer.model[0m
|
42 |
+
[2024-05-27 03:04:28] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/tokenizer.json. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/tokenizer.json[0m
|
43 |
+
[2024-05-27 03:04:28] INFO gen_config.py:156: [91mNot found[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/vocab.json
|
44 |
+
[2024-05-27 03:04:28] INFO gen_config.py:156: [91mNot found[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/merges.txt
|
45 |
+
[2024-05-27 03:04:28] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/added_tokens.json. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/added_tokens.json[0m
|
46 |
+
[2024-05-27 03:04:28] INFO gen_config.py:154: [92mFound[0m tokenizer config: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/tokenizer_config.json. Copying to [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/tokenizer_config.json[0m
|
47 |
+
[2024-05-27 03:04:28] INFO gen_config.py:215: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True}
|
48 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mtemperature[0m: 1.0
|
49 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mpresence_penalty[0m: 0.0
|
50 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mfrequency_penalty[0m: 0.0
|
51 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mrepetition_penalty[0m: 1.0
|
52 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mtop_p[0m: 1.0
|
53 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mmean_gen_len[0m: 128
|
54 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mmax_gen_len[0m: 512
|
55 |
+
[2024-05-27 03:04:28] INFO gen_config.py:31: [System default] Setting [1mshift_fill_factor[0m: 0.3
|
56 |
+
/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/pydantic/main.py:347: UserWarning: Pydantic serializer warnings:
|
57 |
+
Expected `int` but got `list` - serialized value may not be as expected
|
58 |
+
return self.__pydantic_serializer__.to_python(
|
59 |
+
[2024-05-27 03:04:28] INFO gen_config.py:222: Dumping configuration file to: [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/mlc-chat-config.json[0m
|
60 |
+
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd1/rickzhou/models/Phi-3-mini-4k-instruct --quantization q0f32 --source-format auto --output /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC
|
61 |
+
[2024-05-27 03:04:29] INFO auto_config.py:115: [92mFound[0m model configuration: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/config.json
|
62 |
+
[2024-05-27 03:04:30] INFO auto_device.py:79: [92mFound[0m device: cuda:0
|
63 |
+
[2024-05-27 03:04:30] INFO auto_device.py:79: [92mFound[0m device: cuda:1
|
64 |
+
[2024-05-27 03:04:31] INFO auto_device.py:88: [91mNot found[0m device: rocm:0
|
65 |
+
[2024-05-27 03:04:32] INFO auto_device.py:88: [91mNot found[0m device: metal:0
|
66 |
+
[2024-05-27 03:04:34] INFO auto_device.py:79: [92mFound[0m device: vulkan:0
|
67 |
+
[2024-05-27 03:04:34] INFO auto_device.py:79: [92mFound[0m device: vulkan:1
|
68 |
+
[2024-05-27 03:04:34] INFO auto_device.py:79: [92mFound[0m device: vulkan:2
|
69 |
+
[2024-05-27 03:04:35] INFO auto_device.py:88: [91mNot found[0m device: opencl:0
|
70 |
+
[2024-05-27 03:04:35] INFO auto_device.py:35: Using device: [1mcuda:0[0m
|
71 |
+
[2024-05-27 03:04:35] INFO auto_weight.py:70: Finding weights in: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct
|
72 |
+
[2024-05-27 03:04:35] INFO auto_weight.py:136: [91mNot found[0m Huggingface PyTorch
|
73 |
+
[2024-05-27 03:04:35] INFO auto_weight.py:143: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/model.safetensors.index.json
|
74 |
+
[2024-05-27 03:04:35] INFO auto_weight.py:106: Using source weight configuration: [1m/ssd1/rickzhou/models/Phi-3-mini-4k-instruct/model.safetensors.index.json[0m. Use `--source` to override.
|
75 |
+
[2024-05-27 03:04:35] INFO auto_weight.py:110: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override.
|
76 |
+
[2024-05-27 03:04:35] INFO auto_config.py:153: [92mFound[0m model type: [1mphi3[0m. Use `--model-type` to override.
|
77 |
+
[2024-05-27 03:04:35] INFO phi3_model.py:53: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (4096)
|
78 |
+
[2024-05-27 03:04:35] INFO phi3_model.py:68: [1mprefill_chunk_size[0m defaults to 2048
|
79 |
+
[1mWeight conversion with arguments:[0m
|
80 |
+
[1m--config[0m /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/config.json
|
81 |
+
[1m--quantization[0m NoQuantize(name='q0f32', kind='no-quant', model_dtype='float32')
|
82 |
+
[1m--model-type[0m phi3
|
83 |
+
[1m--device[0m cuda:0
|
84 |
+
[1m--source[0m /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/model.safetensors.index.json
|
85 |
+
[1m--source-format[0m huggingface-safetensor
|
86 |
+
[1m--output[0m /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC
|
87 |
+
Start storing to cache /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC
|
88 |
+
|
89 |
0%| | 0/195 [00:00<?, ?it/s]
|
90 |
|
91 |
+
|
92 |
0%| | 0/195 [00:00<?, ?it/s]
|
93 |
|
94 |
+
|
95 |
0%| | 0/195 [00:06<?, ?it/s]/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
|
96 |
+
setattr(self, word, getattr(machar, word).flat[0])
|
97 |
+
/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
|
98 |
+
return self._float_to_str(self.smallest_subnormal)
|
99 |
+
|
100 |
1%| | 1/195 [00:08<26:16, 8.13s/it]
|
101 |
|
102 |
+
|
103 |
1%| | 1/195 [00:08<26:16, 8.13s/it]
|
104 |
|
105 |
+
|
106 |
1%| | 1/195 [00:08<26:16, 8.13s/it]
|
107 |
2%|▏ | 3/195 [00:08<07:05, 2.22s/it]
|
108 |
|
109 |
+
|
110 |
2%|▏ | 3/195 [00:08<07:05, 2.22s/it]
|
111 |
2%|▏ | 4/195 [00:08<05:13, 1.64s/it]
|
112 |
|
113 |
+
|
114 |
2%|▏ | 4/195 [00:08<05:13, 1.64s/it]
|
115 |
|
116 |
+
|
117 |
2%|▏ | 4/195 [00:09<05:13, 1.64s/it]
|
118 |
3%|▎ | 6/195 [00:09<02:50, 1.11it/s]
|
119 |
|
120 |
+
|
121 |
3%|▎ | 6/195 [00:09<02:50, 1.11it/s]
|
122 |
|
123 |
+
|
124 |
3%|▎ | 6/195 [00:09<02:50, 1.11it/s]
|
125 |
4%|▍ | 8/195 [00:09<01:49, 1.71it/s]
|
126 |
|
127 |
+
|
128 |
4%|▍ | 8/195 [00:09<01:49, 1.71it/s]
|
129 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
130 |
|
131 |
+
|
132 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
133 |
|
134 |
+
|
135 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
136 |
|
137 |
+
|
138 |
5%|▍ | 9/195 [00:10<01:47, 1.72it/s]
|
139 |
6%|▌ | 12/195 [00:10<01:05, 2.79it/s]
|
140 |
|
141 |
+
|
142 |
6%|▌ | 12/195 [00:10<01:05, 2.79it/s]
|
143 |
|
144 |
+
|
145 |
6%|▌ | 12/195 [00:10<01:05, 2.79it/s]
|
146 |
7%|▋ | 14/195 [00:10<00:52, 3.46it/s]
|
147 |
|
148 |
+
|
149 |
7%|▋ | 14/195 [00:10<00:52, 3.46it/s]
|
150 |
8%|▊ | 15/195 [00:11<01:00, 2.98it/s]
|
151 |
|
152 |
+
|
153 |
8%|▊ | 15/195 [00:11<01:00, 2.98it/s]
|
154 |
|
155 |
+
|
156 |
8%|▊ | 15/195 [00:11<01:00, 2.98it/s]
|
157 |
9%|▊ | 17/195 [00:11<00:42, 4.19it/s]
|
158 |
|
159 |
+
|
160 |
9%|▊ | 17/195 [00:11<00:42, 4.19it/s]
|
161 |
9%|▉ | 18/195 [00:11<00:45, 3.93it/s]
|
162 |
|
163 |
+
|
164 |
9%|▉ | 18/195 [00:11<00:45, 3.93it/s]
|
165 |
|
166 |
+
|
167 |
9%|▉ | 18/195 [00:11<00:45, 3.93it/s]
|
168 |
10%|█ | 20/195 [00:12<00:37, 4.70it/s]
|
169 |
|
170 |
+
|
171 |
10%|█ | 20/195 [00:12<00:37, 4.70it/s]
|
172 |
11%|█ | 21/195 [00:12<00:48, 3.56it/s]
|
173 |
|
174 |
+
|
175 |
11%|█ | 21/195 [00:12<00:48, 3.56it/s]
|
176 |
|
177 |
+
|
178 |
11%|█ | 21/195 [00:12<00:48, 3.56it/s]
|
179 |
12%|█▏ | 23/195 [00:12<00:33, 5.06it/s]
|
180 |
|
181 |
+
|
182 |
12%|█▏ | 23/195 [00:12<00:33, 5.06it/s]
|
183 |
12%|█▏ | 24/195 [00:13<00:37, 4.54it/s]
|
184 |
|
185 |
+
|
186 |
12%|█▏ | 24/195 [00:13<00:37, 4.54it/s]
|
187 |
|
188 |
+
|
189 |
12%|█▏ | 24/195 [00:13<00:37, 4.54it/s]
|
190 |
13%|█▎ | 26/195 [00:13<00:32, 5.27it/s]
|
191 |
|
192 |
+
|
193 |
13%|█▎ | 26/195 [00:13<00:32, 5.27it/s]
|
194 |
14%|█▍ | 27/195 [00:13<00:44, 3.78it/s]
|
195 |
|
196 |
+
|
197 |
14%|█▍ | 27/195 [00:13<00:44, 3.78it/s]
|
198 |
|
199 |
+
|
200 |
14%|█▍ | 27/195 [00:13<00:44, 3.78it/s]
|
201 |
15%|█▍ | 29/195 [00:13<00:30, 5.37it/s]
|
202 |
|
203 |
+
|
204 |
15%|█▍ | 29/195 [00:13<00:30, 5.37it/s]
|
205 |
15%|█▌ | 30/195 [00:14<00:35, 4.71it/s]
|
206 |
|
207 |
+
|
208 |
15%|█▌ | 30/195 [00:14<00:35, 4.71it/s]
|
209 |
|
210 |
+
|
211 |
15%|█▌ | 30/195 [00:14<00:35, 4.71it/s]
|
212 |
16%|█▋ | 32/195 [00:14<00:30, 5.39it/s]
|
213 |
|
214 |
+
|
215 |
16%|█▋ | 32/195 [00:14<00:30, 5.39it/s]
|
216 |
17%|█▋ | 33/195 [00:15<00:42, 3.82it/s]
|
217 |
|
218 |
+
|
219 |
17%|█▋ | 33/195 [00:15<00:42, 3.82it/s]
|
220 |
|
221 |
+
|
222 |
17%|█▋ | 33/195 [00:15<00:42, 3.82it/s]
|
223 |
18%|█▊ | 35/195 [00:15<00:29, 5.44it/s]
|
224 |
|
225 |
+
|
226 |
18%|█▊ | 35/195 [00:15<00:29, 5.44it/s]
|
227 |
18%|█▊ | 36/195 [00:15<00:33, 4.76it/s]
|
228 |
|
229 |
+
|
230 |
18%|█▊ | 36/195 [00:15<00:33, 4.76it/s]
|
231 |
|
232 |
+
|
233 |
18%|█▊ | 36/195 [00:15<00:33, 4.76it/s]
|
234 |
19%|█▉ | 38/195 [00:15<00:28, 5.45it/s]
|
235 |
|
236 |
+
|
237 |
19%|█▉ | 38/195 [00:15<00:28, 5.45it/s]
|
238 |
20%|██ | 39/195 [00:16<00:40, 3.85it/s]
|
239 |
|
240 |
+
|
241 |
20%|██ | 39/195 [00:16<00:40, 3.85it/s]
|
242 |
|
243 |
+
|
244 |
20%|██ | 39/195 [00:16<00:40, 3.85it/s]
|
245 |
21%|██ | 41/195 [00:16<00:28, 5.48it/s]
|
246 |
|
247 |
+
|
248 |
21%|██ | 41/195 [00:16<00:28, 5.48it/s]
|
249 |
22%|██▏ | 42/195 [00:16<00:32, 4.75it/s]
|
250 |
|
251 |
+
|
252 |
22%|██▏ | 42/195 [00:16<00:32, 4.75it/s]
|
253 |
|
254 |
+
|
255 |
22%|██▏ | 42/195 [00:16<00:32, 4.75it/s]
|
256 |
23%|██▎ | 44/195 [00:17<00:27, 5.43it/s]
|
257 |
|
258 |
+
|
259 |
23%|██▎ | 44/195 [00:17<00:27, 5.43it/s]
|
260 |
23%|██▎ | 45/195 [00:17<00:39, 3.83it/s]
|
261 |
|
262 |
+
|
263 |
23%|██▎ | 45/195 [00:17<00:39, 3.83it/s]
|
264 |
|
265 |
+
|
266 |
23%|██▎ | 45/195 [00:17<00:39, 3.83it/s]
|
267 |
24%|██▍ | 47/195 [00:17<00:27, 5.44it/s]
|
268 |
|
269 |
+
|
270 |
24%|██▍ | 47/195 [00:17<00:27, 5.44it/s]
|
271 |
25%|██▍ | 48/195 [00:18<00:30, 4.75it/s]
|
272 |
|
273 |
+
|
274 |
25%|██▍ | 48/195 [00:18<00:30, 4.75it/s]
|
275 |
|
276 |
+
|
277 |
25%|██▍ | 48/195 [00:18<00:30, 4.75it/s]
|
278 |
26%|██▌ | 50/195 [00:18<00:26, 5.43it/s]
|
279 |
|
280 |
+
|
281 |
26%|██▌ | 50/195 [00:18<00:26, 5.43it/s]
|
282 |
26%|██▌ | 51/195 [00:18<00:37, 3.82it/s]
|
283 |
|
284 |
+
|
285 |
26%|██▌ | 51/195 [00:18<00:37, 3.82it/s]
|
286 |
|
287 |
+
|
288 |
26%|██▌ | 51/195 [00:18<00:37, 3.82it/s]
|
289 |
27%|██▋ | 53/195 [00:18<00:26, 5.44it/s]
|
290 |
|
291 |
+
|
292 |
27%|██▋ | 53/195 [00:18<00:26, 5.44it/s]
|
293 |
28%|██▊ | 54/195 [00:19<00:29, 4.74it/s]
|
294 |
|
295 |
+
|
296 |
28%|██▊ | 54/195 [00:19<00:29, 4.74it/s]
|
297 |
|
298 |
+
|
299 |
28%|██▊ | 54/195 [00:19<00:29, 4.74it/s]
|
300 |
29%|██▊ | 56/195 [00:19<00:25, 5.38it/s]
|
301 |
|
302 |
+
|
303 |
29%|██▊ | 56/195 [00:19<00:25, 5.38it/s]
|
304 |
29%|██▉ | 57/195 [00:20<00:36, 3.80it/s]
|
305 |
|
306 |
+
|
307 |
29%|██▉ | 57/195 [00:20<00:36, 3.80it/s]
|
308 |
|
309 |
+
|
310 |
29%|██▉ | 57/195 [00:20<00:36, 3.80it/s]
|
311 |
30%|███ | 59/195 [00:20<00:25, 5.41it/s]
|
312 |
|
313 |
+
|
314 |
30%|███ | 59/195 [00:20<00:25, 5.41it/s]
|
315 |
31%|███ | 60/195 [00:20<00:28, 4.73it/s]
|
316 |
|
317 |
+
|
318 |
31%|███ | 60/195 [00:20<00:28, 4.73it/s]
|
319 |
|
320 |
+
|
321 |
31%|███ | 60/195 [00:20<00:28, 4.73it/s]
|
322 |
32%|███▏ | 62/195 [00:20<00:24, 5.41it/s]
|
323 |
|
324 |
+
|
325 |
32%|███▏ | 62/195 [00:20<00:24, 5.41it/s]
|
326 |
32%|███▏ | 63/195 [00:21<00:34, 3.82it/s]
|
327 |
|
328 |
+
|
329 |
32%|███▏ | 63/195 [00:21<00:34, 3.82it/s]
|
330 |
|
331 |
+
|
332 |
32%|███▏ | 63/195 [00:21<00:34, 3.82it/s]
|
333 |
33%|███▎ | 65/195 [00:21<00:23, 5.44it/s]
|
334 |
|
335 |
+
|
336 |
33%|███▎ | 65/195 [00:21<00:23, 5.44it/s]
|
337 |
34%|███▍ | 66/195 [00:21<00:27, 4.74it/s]
|
338 |
|
339 |
+
|
340 |
34%|███▍ | 66/195 [00:21<00:27, 4.74it/s]
|
341 |
|
342 |
+
|
343 |
34%|███▍ | 66/195 [00:21<00:27, 4.74it/s]
|
344 |
|
345 |
+
|
346 |
34%|███▍ | 66/195 [00:22<00:27, 4.74it/s]
|
347 |
|
348 |
+
|
349 |
34%|███▍ | 66/195 [00:32<00:27, 4.74it/s]
|
350 |
35%|███▍ | 68/195 [00:33<04:46, 2.25s/it]
|
351 |
|
352 |
+
|
353 |
35%|███▍ | 68/195 [00:33<04:46, 2.25s/it]
|
354 |
|
355 |
+
|
356 |
35%|███▍ | 68/195 [00:33<04:46, 2.25s/it]
|
357 |
36%|███▌ | 70/195 [00:33<03:09, 1.52s/it]
|
358 |
|
359 |
+
|
360 |
36%|███▌ | 70/195 [00:33<03:09, 1.52s/it]
|
361 |
36%|███▋ | 71/195 [00:33<02:43, 1.32s/it]
|
362 |
|
363 |
+
|
364 |
36%|███▋ | 71/195 [00:33<02:43, 1.32s/it]
|
365 |
|
366 |
+
|
367 |
36%|███▋ | 71/195 [00:33<02:43, 1.32s/it]
|
368 |
37%|███▋ | 73/195 [00:33<01:44, 1.16it/s]
|
369 |
|
370 |
+
|
371 |
37%|███▋ | 73/195 [00:33<01:44, 1.16it/s]
|
372 |
38%|███▊ | 74/195 [00:34<01:30, 1.34it/s]
|
373 |
|
374 |
+
|
375 |
38%|███▊ | 74/195 [00:34<01:30, 1.34it/s]
|
376 |
|
377 |
+
|
378 |
38%|███▊ | 74/195 [00:34<01:30, 1.34it/s]
|
379 |
39%|███▉ | 76/195 [00:34<01:01, 1.92it/s]
|
380 |
|
381 |
+
|
382 |
39%|███▉ | 76/195 [00:34<01:01, 1.92it/s]
|
383 |
39%|███▉ | 77/195 [00:35<01:01, 1.91it/s]
|
384 |
|
385 |
+
|
386 |
39%|███▉ | 77/195 [00:35<01:01, 1.91it/s]
|
387 |
|
388 |
+
|
389 |
39%|███▉ | 77/195 [00:35<01:01, 1.91it/s]
|
390 |
41%|████ | 79/195 [00:35<00:40, 2.87it/s]
|
391 |
|
392 |
+
|
393 |
41%|████ | 79/195 [00:35<00:40, 2.87it/s]
|
394 |
41%|████ | 80/195 [00:35<00:38, 2.95it/s]
|
395 |
|
396 |
+
|
397 |
41%|████ | 80/195 [00:35<00:38, 2.95it/s]
|
398 |
|
399 |
+
|
400 |
41%|████ | 80/195 [00:35<00:38, 2.95it/s]
|
401 |
42%|████▏ | 82/195 [00:35<00:29, 3.80it/s]
|
402 |
|
403 |
+
|
404 |
42%|████▏ | 82/195 [00:35<00:29, 3.80it/s]
|
405 |
43%|████▎ | 83/195 [00:36<00:35, 3.12it/s]
|
406 |
|
407 |
+
|
408 |
43%|████▎ | 83/195 [00:36<00:35, 3.12it/s]
|
409 |
|
410 |
+
|
411 |
43%|████▎ | 83/195 [00:36<00:35, 3.12it/s]
|
412 |
44%|████▎ | 85/195 [00:36<00:24, 4.53it/s]
|
413 |
|
414 |
+
|
415 |
44%|████▎ | 85/195 [00:36<00:24, 4.53it/s]
|
416 |
44%|████▍ | 86/195 [00:36<00:25, 4.20it/s]
|
417 |
|
418 |
+
|
419 |
44%|████▍ | 86/195 [00:36<00:25, 4.20it/s]
|
420 |
|
421 |
+
|
422 |
44%|████▍ | 86/195 [00:36<00:25, 4.20it/s]
|
423 |
45%|████▌ | 88/195 [00:36<00:21, 4.99it/s]
|
424 |
|
425 |
+
|
426 |
45%|████▌ | 88/195 [00:37<00:21, 4.99it/s]
|
427 |
46%|████▌ | 89/195 [00:37<00:28, 3.68it/s]
|
428 |
|
429 |
+
|
430 |
46%|████▌ | 89/195 [00:37<00:28, 3.68it/s]
|
431 |
|
432 |
+
|
433 |
46%|████▌ | 89/195 [00:37<00:28, 3.68it/s]
|
434 |
47%|████▋ | 91/195 [00:37<00:19, 5.25it/s]
|
435 |
|
436 |
+
|
437 |
47%|████▋ | 91/195 [00:37<00:19, 5.25it/s]
|
438 |
47%|████▋ | 92/195 [00:37<00:22, 4.67it/s]
|
439 |
|
440 |
+
|
441 |
47%|████▋ | 92/195 [00:37<00:22, 4.67it/s]
|
442 |
|
443 |
+
|
444 |
47%|████▋ | 92/195 [00:37<00:22, 4.67it/s]
|
445 |
48%|████▊ | 94/195 [00:38<00:18, 5.40it/s]
|
446 |
|
447 |
+
|
448 |
48%|████▊ | 94/195 [00:38<00:18, 5.40it/s]
|
449 |
49%|████▊ | 95/195 [00:38<00:25, 3.85it/s]
|
450 |
|
451 |
+
|
452 |
49%|████▊ | 95/195 [00:38<00:25, 3.85it/s]
|
453 |
|
454 |
+
|
455 |
49%|████▊ | 95/195 [00:38<00:25, 3.85it/s]
|
456 |
50%|████▉ | 97/195 [00:38<00:17, 5.48it/s]
|
457 |
|
458 |
+
|
459 |
50%|████▉ | 97/195 [00:38<00:17, 5.48it/s]
|
460 |
50%|█████ | 98/195 [00:39<00:20, 4.81it/s]
|
461 |
|
462 |
+
|
463 |
50%|█████ | 98/195 [00:39<00:20, 4.81it/s]
|
464 |
|
465 |
+
|
466 |
50%|█████ | 98/195 [00:39<00:20, 4.81it/s]
|
467 |
51%|█████▏ | 100/195 [00:39<00:17, 5.50it/s]
|
468 |
|
469 |
+
|
470 |
51%|█████▏ | 100/195 [00:39<00:17, 5.50it/s]
|
471 |
52%|█████▏ | 101/195 [00:39<00:24, 3.90it/s]
|
472 |
|
473 |
+
|
474 |
52%|█████▏ | 101/195 [00:39<00:24, 3.90it/s]
|
475 |
|
476 |
+
|
477 |
52%|█████▏ | 101/195 [00:39<00:24, 3.90it/s]
|
478 |
53%|█████▎ | 103/195 [00:40<00:16, 5.53it/s]
|
479 |
|
480 |
+
|
481 |
53%|█████▎ | 103/195 [00:40<00:16, 5.53it/s]
|
482 |
53%|█████▎ | 104/195 [00:40<00:18, 4.84it/s]
|
483 |
|
484 |
+
|
485 |
53%|█████▎ | 104/195 [00:40<00:18, 4.84it/s]
|
486 |
|
487 |
+
|
488 |
53%|█████▎ | 104/195 [00:40<00:18, 4.84it/s]
|
489 |
54%|█████▍ | 106/195 [00:40<00:16, 5.53it/s]
|
490 |
|
491 |
+
|
492 |
54%|█████▍ | 106/195 [00:40<00:16, 5.53it/s]
|
493 |
55%|█████▍ | 107/195 [00:41<00:22, 3.91it/s]
|
494 |
|
495 |
+
|
496 |
55%|█████▍ | 107/195 [00:41<00:22, 3.91it/s]
|
497 |
|
498 |
+
|
499 |
55%|█████▍ | 107/195 [00:41<00:22, 3.91it/s]
|
500 |
56%|█████▌ | 109/195 [00:41<00:15, 5.55it/s]
|
501 |
|
502 |
+
|
503 |
56%|█████▌ | 109/195 [00:41<00:15, 5.55it/s]
|
504 |
56%|█████▋ | 110/195 [00:41<00:17, 4.84it/s]
|
505 |
|
506 |
+
|
507 |
56%|█████▋ | 110/195 [00:41<00:17, 4.84it/s]
|
508 |
|
509 |
+
|
510 |
56%|█████▋ | 110/195 [00:41<00:17, 4.84it/s]
|
511 |
57%|█████▋ | 112/195 [00:41<00:15, 5.53it/s]
|
512 |
|
513 |
+
|
514 |
57%|█████▋ | 112/195 [00:41<00:15, 5.53it/s]
|
515 |
58%|█████▊ | 113/195 [00:42<00:20, 3.91it/s]
|
516 |
|
517 |
+
|
518 |
58%|█████▊ | 113/195 [00:42<00:20, 3.91it/s]
|
519 |
|
520 |
+
|
521 |
58%|█████▊ | 113/195 [00:42<00:20, 3.91it/s]
|
522 |
59%|█████▉ | 115/195 [00:42<00:14, 5.55it/s]
|
523 |
|
524 |
+
|
525 |
59%|█████▉ | 115/195 [00:42<00:14, 5.55it/s]
|
526 |
59%|█████▉ | 116/195 [00:42<00:16, 4.84it/s]
|
527 |
|
528 |
+
|
529 |
59%|█████▉ | 116/195 [00:42<00:16, 4.84it/s]
|
530 |
|
531 |
+
|
532 |
59%|█████▉ | 116/195 [00:42<00:16, 4.84it/s]
|
533 |
61%|██████ | 118/195 [00:43<00:13, 5.51it/s]
|
534 |
|
535 |
+
|
536 |
61%|██████ | 118/195 [00:43<00:13, 5.51it/s]
|
537 |
61%|██████ | 119/195 [00:43<00:19, 3.89it/s]
|
538 |
|
539 |
+
|
540 |
61%|██████ | 119/195 [00:43<00:19, 3.89it/s]
|
541 |
|
542 |
+
|
543 |
61%|██████ | 119/195 [00:43<00:19, 3.89it/s]
|
544 |
62%|██████▏ | 121/195 [00:43<00:13, 5.53it/s]
|
545 |
|
546 |
+
|
547 |
62%|██████▏ | 121/195 [00:43<00:13, 5.53it/s]
|
548 |
63%|██████▎ | 122/195 [00:44<00:15, 4.83it/s]
|
549 |
|
550 |
+
|
551 |
63%|██████▎ | 122/195 [00:44<00:15, 4.83it/s]
|
552 |
|
553 |
+
|
554 |
63%|██████▎ | 122/195 [00:44<00:15, 4.83it/s]
|
555 |
64%|██████▎ | 124/195 [00:44<00:12, 5.53it/s]
|
556 |
|
557 |
+
|
558 |
64%|██████▎ | 124/195 [00:44<00:12, 5.53it/s]
|
559 |
64%|██████▍ | 125/195 [00:44<00:17, 3.91it/s]
|
560 |
|
561 |
+
|
562 |
64%|██████▍ | 125/195 [00:44<00:17, 3.91it/s]
|
563 |
|
564 |
+
|
565 |
64%|██████▍ | 125/195 [00:44<00:17, 3.91it/s]
|
566 |
65%|██████▌ | 127/195 [00:44<00:12, 5.54it/s]
|
567 |
|
568 |
+
|
569 |
65%|██████▌ | 127/195 [00:45<00:12, 5.54it/s]
|
570 |
66%|██████▌ | 128/195 [00:45<00:13, 4.82it/s]
|
571 |
|
572 |
+
|
573 |
66%|██████▌ | 128/195 [00:45<00:13, 4.82it/s]
|
574 |
|
575 |
+
|
576 |
66%|██████▌ | 128/195 [00:45<00:13, 4.82it/s]
|
577 |
67%|██████▋ | 130/195 [00:45<00:11, 5.51it/s]
|
578 |
|
579 |
+
|
580 |
67%|██████▋ | 130/195 [00:45<00:11, 5.51it/s]
|
581 |
67%|██████▋ | 131/195 [00:46<00:16, 3.91it/s]
|
582 |
|
583 |
+
|
584 |
67%|██████▋ | 131/195 [00:46<00:16, 3.91it/s]
|
585 |
|
586 |
+
|
587 |
67%|██████▋ | 131/195 [00:46<00:16, 3.91it/s]
|
588 |
68%|██████▊ | 133/195 [00:46<00:11, 5.55it/s]
|
589 |
|
590 |
+
|
591 |
68%|██████▊ | 133/195 [00:46<00:11, 5.55it/s]
|
592 |
69%|██████▊ | 134/195 [00:46<00:12, 4.85it/s]
|
593 |
|
594 |
+
|
595 |
69%|██████▊ | 134/195 [00:46<00:12, 4.85it/s]
|
596 |
|
597 |
+
|
598 |
69%|██████▊ | 134/195 [00:46<00:12, 4.85it/s]
|
599 |
70%|██████▉ | 136/195 [00:46<00:10, 5.53it/s]
|
600 |
|
601 |
+
|
602 |
70%|██████▉ | 136/195 [00:46<00:10, 5.53it/s]
|
603 |
70%|███████ | 137/195 [00:47<00:14, 3.92it/s]
|
604 |
|
605 |
+
|
606 |
70%|███████ | 137/195 [00:47<00:14, 3.92it/s]
|
607 |
|
608 |
+
|
609 |
70%|███████ | 137/195 [00:47<00:14, 3.92it/s]
|
610 |
71%|███████▏ | 139/195 [00:47<00:10, 5.56it/s]
|
611 |
|
612 |
+
|
613 |
71%|███████▏ | 139/195 [00:47<00:10, 5.56it/s]
|
614 |
72%|███████▏ | 140/195 [00:47<00:11, 4.85it/s]
|
615 |
|
616 |
+
|
617 |
72%|███████▏ | 140/195 [00:47<00:11, 4.85it/s]
|
618 |
|
619 |
+
|
620 |
72%|███████▏ | 140/195 [00:47<00:11, 4.85it/s]
|
621 |
73%|███████▎ | 142/195 [00:48<00:09, 5.54it/s]
|
622 |
|
623 |
+
|
624 |
73%|███████▎ | 142/195 [00:48<00:09, 5.54it/s]
|
625 |
73%|███████▎ | 143/195 [00:48<00:13, 3.92it/s]
|
626 |
|
627 |
+
|
628 |
73%|███████▎ | 143/195 [00:48<00:13, 3.92it/s]
|
629 |
|
630 |
+
|
631 |
73%|███████▎ | 143/195 [00:48<00:13, 3.92it/s]
|
632 |
74%|███████▍ | 145/195 [00:48<00:09, 5.55it/s]
|
633 |
|
634 |
+
|
635 |
74%|███████▍ | 145/195 [00:48<00:09, 5.55it/s]
|
636 |
75%|███████▍ | 146/195 [00:48<00:10, 4.84it/s]
|
637 |
|
638 |
+
|
639 |
75%|███████▍ | 146/195 [00:48<00:10, 4.84it/s]
|
640 |
|
641 |
+
|
642 |
75%|███████▍ | 146/195 [00:48<00:10, 4.84it/s]
|
643 |
76%|███████▌ | 148/195 [00:49<00:08, 5.51it/s]
|
644 |
|
645 |
+
|
646 |
76%|███████▌ | 148/195 [00:49<00:08, 5.51it/s]
|
647 |
76%|███████▋ | 149/195 [00:49<00:11, 3.88it/s]
|
648 |
|
649 |
+
|
650 |
76%|███████▋ | 149/195 [00:49<00:11, 3.88it/s]
|
651 |
|
652 |
+
|
653 |
76%|███████▋ | 149/195 [00:49<00:11, 3.88it/s]
|
654 |
77%|███████▋ | 151/195 [00:49<00:07, 5.51it/s]
|
655 |
|
656 |
+
|
657 |
77%|███████▋ | 151/195 [00:49<00:07, 5.51it/s]
|
658 |
78%|███████▊ | 152/195 [00:50<00:08, 4.82it/s]
|
659 |
|
660 |
+
|
661 |
78%|███████▊ | 152/195 [00:50<00:08, 4.82it/s]
|
662 |
78%|███████▊ | 153/195 [00:50<00:07, 5.45it/s]
|
663 |
|
664 |
+
|
665 |
78%|███████▊ | 153/195 [00:50<00:07, 5.45it/s]
|
666 |
|
667 |
+
|
668 |
78%|███████▊ | 153/195 [00:50<00:07, 5.45it/s]
|
669 |
79%|███████▉ | 155/195 [00:50<00:06, 6.01it/s]
|
670 |
|
671 |
+
|
672 |
79%|███████▉ | 155/195 [00:50<00:06, 6.01it/s]
|
673 |
80%|████████ | 156/195 [00:51<00:09, 4.02it/s]
|
674 |
|
675 |
+
|
676 |
80%|████████ | 156/195 [00:51<00:09, 4.02it/s]
|
677 |
|
678 |
+
|
679 |
80%|████████ | 156/195 [00:51<00:09, 4.02it/s]
|
680 |
81%|████████ | 158/195 [00:51<00:06, 5.75it/s]
|
681 |
|
682 |
+
|
683 |
81%|████████ | 158/195 [00:51<00:06, 5.75it/s]
|
684 |
82%|████████▏ | 159/195 [00:51<00:07, 4.95it/s]
|
685 |
|
686 |
+
|
687 |
82%|████████▏ | 159/195 [00:51<00:07, 4.95it/s]
|
688 |
|
689 |
+
|
690 |
82%|████████▏ | 159/195 [00:51<00:07, 4.95it/s]
|
691 |
83%|████████▎ | 161/195 [00:51<00:06, 5.60it/s]
|
692 |
|
693 |
+
|
694 |
83%|████████▎ | 161/195 [00:51<00:06, 5.60it/s]
|
695 |
83%|████████▎ | 162/195 [00:52<00:08, 3.89it/s]
|
696 |
|
697 |
+
|
698 |
83%|████████▎ | 162/195 [00:52<00:08, 3.89it/s]
|
699 |
|
700 |
+
|
701 |
83%|████████▎ | 162/195 [00:52<00:08, 3.89it/s]
|
702 |
84%|████████▍ | 164/195 [00:52<00:05, 5.54it/s]
|
703 |
|
704 |
+
|
705 |
84%|████████▍ | 164/195 [00:52<00:05, 5.54it/s]
|
706 |
85%|████████▍ | 165/195 [00:52<00:06, 4.83it/s]
|
707 |
|
708 |
+
|
709 |
85%|████████▍ | 165/195 [00:52<00:06, 4.83it/s]
|
710 |
|
711 |
+
|
712 |
85%|████████▍ | 165/195 [00:52<00:06, 4.83it/s]
|
713 |
86%|████████▌ | 167/195 [00:53<00:05, 5.43it/s]
|
714 |
|
715 |
+
|
716 |
86%|████████▌ | 167/195 [00:53<00:05, 5.43it/s]
|
717 |
86%|████████▌ | 168/195 [00:53<00:07, 3.85it/s]
|
718 |
|
719 |
+
|
720 |
86%|████████▌ | 168/195 [00:53<00:07, 3.85it/s]
|
721 |
|
722 |
+
|
723 |
86%|████████▌ | 168/195 [00:53<00:07, 3.85it/s]
|
724 |
87%|████████▋ | 170/195 [00:53<00:04, 5.47it/s]
|
725 |
|
726 |
+
|
727 |
87%|████████▋ | 170/195 [00:53<00:04, 5.47it/s]
|
728 |
88%|████████▊ | 171/195 [00:54<00:05, 4.80it/s]
|
729 |
|
730 |
+
|
731 |
88%|████████▊ | 171/195 [00:54<00:05, 4.80it/s]
|
732 |
|
733 |
+
|
734 |
88%|████████▊ | 171/195 [00:54<00:05, 4.80it/s]
|
735 |
89%|████████▊ | 173/195 [00:54<00:03, 5.51it/s]
|
736 |
|
737 |
+
|
738 |
89%|████████▊ | 173/195 [00:54<00:03, 5.51it/s]
|
739 |
89%|████████▉ | 174/195 [00:54<00:05, 3.92it/s]
|
740 |
|
741 |
+
|
742 |
89%|████████▉ | 174/195 [00:54<00:05, 3.92it/s]
|
743 |
|
744 |
+
|
745 |
89%|████████▉ | 174/195 [00:54<00:05, 3.92it/s]
|
746 |
90%|█████████ | 176/195 [00:54<00:03, 5.56it/s]
|
747 |
|
748 |
+
|
749 |
90%|█████████ | 176/195 [00:54<00:03, 5.56it/s]
|
750 |
91%|█████████ | 177/195 [00:55<00:03, 4.86it/s]
|
751 |
|
752 |
+
|
753 |
91%|█████████ | 177/195 [00:55<00:03, 4.86it/s]
|
754 |
|
755 |
+
|
756 |
91%|█████████ | 177/195 [00:55<00:03, 4.86it/s]
|
757 |
92%|█████████▏| 179/195 [00:55<00:02, 5.54it/s]
|
758 |
|
759 |
+
|
760 |
92%|█████████▏| 179/195 [00:55<00:02, 5.54it/s]
|
761 |
92%|█████████▏| 180/195 [00:56<00:03, 3.90it/s]
|
762 |
|
763 |
+
|
764 |
92%|█████████▏| 180/195 [00:56<00:03, 3.90it/s]
|
765 |
|
766 |
+
|
767 |
92%|█████████▏| 180/195 [00:56<00:03, 3.90it/s]
|
768 |
93%|█████████▎| 182/195 [00:56<00:02, 5.54it/s]
|
769 |
|
770 |
+
|
771 |
93%|█████████▎| 182/195 [00:56<00:02, 5.54it/s]
|
772 |
94%|█████████▍| 183/195 [00:56<00:02, 4.87it/s]
|
773 |
|
774 |
+
|
775 |
94%|█████████▍| 183/195 [00:56<00:02, 4.87it/s]
|
776 |
|
777 |
+
|
778 |
94%|█████████▍| 183/195 [00:56<00:02, 4.87it/s]
|
779 |
95%|█████████▍| 185/195 [00:56<00:01, 5.56it/s]
|
780 |
|
781 |
+
|
782 |
95%|█████████▍| 185/195 [00:56<00:01, 5.56it/s]
|
783 |
95%|█████████▌| 186/195 [00:57<00:02, 3.88it/s]
|
784 |
|
785 |
+
|
786 |
95%|█████████▌| 186/195 [00:57<00:02, 3.88it/s]
|
787 |
|
788 |
+
|
789 |
95%|█████████▌| 186/195 [00:57<00:02, 3.88it/s]
|
790 |
96%|█████████▋| 188/195 [00:57<00:01, 5.46it/s]
|
791 |
|
792 |
+
|
793 |
96%|█████████▋| 188/195 [00:57<00:01, 5.46it/s]
|
794 |
97%|█████████▋| 189/195 [00:57<00:01, 4.81it/s]
|
795 |
|
796 |
+
|
797 |
97%|█████████▋| 189/195 [00:57<00:01, 4.81it/s]
|
798 |
|
799 |
+
|
800 |
97%|��████████▋| 189/195 [00:57<00:01, 4.81it/s]
|
801 |
98%|█████████▊| 191/195 [00:57<00:00, 5.52it/s]
|
802 |
|
803 |
+
|
804 |
98%|█████████▊| 191/195 [00:58<00:00, 5.52it/s]
|
805 |
98%|█████████▊| 192/195 [00:58<00:00, 3.92it/s]
|
806 |
|
807 |
+
|
808 |
98%|█████████▊| 192/195 [00:58<00:00, 3.92it/s]
|
809 |
|
810 |
+
|
811 |
98%|█████████▊| 192/195 [00:58<00:00, 3.92it/s]
|
812 |
99%|█████████▉| 194/195 [00:58<00:00, 5.56it/s]
|
813 |
|
814 |
+
|
815 |
99%|█████████▉| 194/195 [00:58<00:00, 5.56it/s]
|
816 |
+
[2024-05-27 03:05:36] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct/model-00001-of-00002.safetensors
|
817 |
+
[2024-05-27 03:05:36] INFO stats.py:76: [92mTime usage[0m: HF loading: 16.976 sec; Pre-quantization mapping: 1.975 sec; Quantization: 0.000 sec
|
818 |
+
[2024-05-27 03:05:36] INFO stats.py:90: [92mRAM usage[0m: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
|
819 |
+
[2024-05-27 03:05:36] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 14.235 GB
|
820 |
+
[2024-05-27 03:05:36] INFO convert_weight.py:160: [92mTotal parameters[0m: 3,821,079,552
|
821 |
+
[2024-05-27 03:05:36] INFO convert_weight.py:161: [92mBits per parameter[0m: 32.000
|
822 |
+
[2024-05-27 03:05:36] INFO convert_weight.py:166: Saved to directory: [1m/ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC[0m
|
823 |
+
|
824 |
+
All finished, 130 total shards committed, record saved to /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/ndarray-cache.json
|
825 |
+
Also saved a bf16 record to /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-4k-instruct-q0f32-MLC/ndarray-cache-b16.json
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"field_model_type": "phi3",
|
4 |
+
"quantization": "q0f32",
|
5 |
+
"field_model_config": {
|
6 |
+
"model_type": "phi3",
|
7 |
+
"hidden_size": 3072,
|
8 |
+
"vocab_size": 32064,
|
9 |
+
"num_hidden_layers": 32,
|
10 |
+
"num_attention_heads": 32,
|
11 |
+
"intermediate_size": 8192,
|
12 |
+
"rms_norm_eps": 1e-05,
|
13 |
+
"num_key_value_heads": 32,
|
14 |
+
"position_embedding_base": 10000.0,
|
15 |
+
"context_window_size": 4096,
|
16 |
+
"prefill_chunk_size": 2048,
|
17 |
+
"head_dim": 96,
|
18 |
+
"tensor_parallel_shards": 1,
|
19 |
+
"max_batch_size": 80
|
20 |
+
},
|
21 |
+
"vocab_size": 32064,
|
22 |
+
"context_window_size": 4096,
|
23 |
+
"sliding_window_size": -1,
|
24 |
+
"prefill_chunk_size": 2048,
|
25 |
+
"attention_sink_size": -1,
|
26 |
+
"tensor_parallel_shards": 1,
|
27 |
+
"temperature": 1.0,
|
28 |
+
"presence_penalty": 0.0,
|
29 |
+
"frequency_penalty": 0.0,
|
30 |
+
"repetition_penalty": 1.0,
|
31 |
+
"top_p": 1.0,
|
32 |
+
"tokenizer_files": [
|
33 |
+
"tokenizer.model",
|
34 |
+
"tokenizer.json",
|
35 |
+
"added_tokens.json",
|
36 |
+
"tokenizer_config.json"
|
37 |
+
],
|
38 |
+
"tokenizer_info": {
|
39 |
+
"token_postproc_method": "byte_fallback",
|
40 |
+
"prepend_space_in_encode": true,
|
41 |
+
"strip_space_in_decode": true
|
42 |
+
},
|
43 |
+
"conv_template": {
|
44 |
+
"name": "phi-3",
|
45 |
+
"system_template": "<|system|>\n{system_message}",
|
46 |
+
"system_message": "You are a helpful digital assistant. Please provide safe, ethical and accurate information to the user.",
|
47 |
+
"system_prefix_token_ids": [
|
48 |
+
1
|
49 |
+
],
|
50 |
+
"add_role_after_system_message": true,
|
51 |
+
"roles": {
|
52 |
+
"user": "<|user|>",
|
53 |
+
"assistant": "<|assistant|>"
|
54 |
+
},
|
55 |
+
"role_templates": {
|
56 |
+
"user": "{user_message}",
|
57 |
+
"assistant": "{assistant_message}",
|
58 |
+
"tool": "{tool_message}"
|
59 |
+
},
|
60 |
+
"messages": [],
|
61 |
+
"seps": [
|
62 |
+
"<|end|>\n"
|
63 |
+
],
|
64 |
+
"role_content_sep": "\n",
|
65 |
+
"role_empty_sep": "\n",
|
66 |
+
"stop_str": [
|
67 |
+
"<|endoftext|>"
|
68 |
+
],
|
69 |
+
"stop_token_ids": [
|
70 |
+
32000,
|
71 |
+
32001,
|
72 |
+
32007
|
73 |
+
],
|
74 |
+
"function_string": "",
|
75 |
+
"use_function_calling": false
|
76 |
+
},
|
77 |
+
"pad_token_id": 32000,
|
78 |
+
"bos_token_id": 1,
|
79 |
+
"eos_token_id": [
|
80 |
+
32000,
|
81 |
+
32001,
|
82 |
+
32007
|
83 |
+
],
|
84 |
+
"mean_gen_len": 128,
|
85 |
+
"max_gen_len": 512,
|
86 |
+
"shift_fill_factor": 0.3
|
87 |
+
}
|
ndarray-cache-b16.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ndarray-cache.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df40c10192dc1d5fb2a479458331624e60788db5eb0fe0f980dbb12fe145d5ce
|
3 |
+
size 197001216
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4ad850b996123270c49e890d324832aef9ad842b0f085a4174c22c6ea9ac4f
|
3 |
+
size 50331648
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:badbb9cb80505c83e58953c232c913bed654cdef67751b6a5b70d5dab8eca86e
|
3 |
+
size 56623104
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:207ebe99c8f06f7288e7ba173d6e36084af20f9c8de4e27ba4b52fcc560334a6
|
3 |
+
size 18874368
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d2d9322f60c900e0ff3364c1f62a7b0d35efcb3b5840a91c364e37992d466ba
|
3 |
+
size 50331648
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:756b23bca7d41c4b433888ab5192f1b650c758de4517763fca3ae6869f559733
|
3 |
+
size 100663296
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f8c99368645eb0d21cd6dfb0264c174654e8129977342f5df0fdcd0179007c3
|
3 |
+
size 18874368
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:850a3986780bb9c3a1e63de782a12d663aae0a79d3c1f7b249017f36996fced3
|
3 |
+
size 56623104
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:568d0db6c28d7b3d6baa666b64345cf2b6836529de0003249bf7e4c8a9bdbcb8
|
3 |
+
size 50331648
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7107f3106c0ee833abed7814b83b829966102f26768b47e6b56d141e2c04b393
|
3 |
+
size 100663296
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6def91230ee779540606cc520b363ccd4a7a465edafe860ce62675fa62ffc2a4
|
3 |
+
size 18874368
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ef70e94a1c3b26fe07d5c8140b2f4dd4f8fd5fc2be2f1077a62f7ec31fd63fa
|
3 |
+
size 56623104
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e35c5f8f8e6e21570c43e1ff5d0d52954b7d1e68182f3069f854bbde76358a0
|
3 |
+
size 50331648
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb65496e2e29c9149be95cb2bf60606203e46c7046cd52dae1bc6ac31cbe910
|
3 |
+
size 50331648
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35cf2575eee6a7d7d64118137c3aab99579e5572a386a6ccb6388dd932c9ed9f
|
3 |
+
size 100663296
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86eb0a68e0f8260a26fdc8901a1e938b90ebdd7f39e5622501232b4b91144920
|
3 |
+
size 18874368
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29941b1c4548474d7349ae2d41ec7a090b551e49ae9baa0948420c72c5fe752d
|
3 |
+
size 56623104
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76184f2b8c3467da81d709db403f96a676f6deae0e82bc02bb1dca9bd20a3544
|
3 |
+
size 50331648
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acd4ffcf9e4789486406d3af35f01e3d24e0c0134cc666ea38a22757a04b5198
|
3 |
+
size 100663296
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8c4c6de39b700f2d8883c09af80c2cb554074aed2cc3a566f4b3f3eb4a21942
|
3 |
+
size 18874368
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d92740f6f3251b459e7796659f2dfb7c6d571bc83e485d40169480268d4b4517
|
3 |
+
size 56623104
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f535eb5e731a9b2f83261e5d16b6e62dc1b581a63e160b47f1f018f042384d75
|
3 |
+
size 50331648
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:940a93cd2993ff0e923f289065cd8b5427ca4a33aff3663523be20571f0a5fb9
|
3 |
+
size 100663296
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c95f7116592c307a1595d8887823ee034b7944bf13c2780eca78e0b338b297c
|
3 |
+
size 18874368
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4b455769067c13c1e5f3702d706acd54280c7b500341d0035cad9b1a319b2cd
|
3 |
+
size 100663296
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e24163d1d43008028d92397784b9ba3b9c58010df8e12714936c07f58a404518
|
3 |
+
size 56623104
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40876c08372b681f538e4bc69e67d16b8a64a4bd550fc79bd2d542b6fa629d4c
|
3 |
+
size 50331648
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16c52e0ce73001358aea309436290c1e3bbfccd70fd2bcadd1338f39acb4676f
|
3 |
+
size 100663296
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4524d9a09a673e8da60d27a1a67c83db7d24328a4ce3492bcc4f9fd145915af8
|
3 |
+
size 18874368
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54217b91a8efb4783c40b3e656d88817119c62b0f048c077bb6c20073f8195fb
|
3 |
+
size 56623104
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd7b2cec79a4030e9b409d26b79f90699ff5d28a2231131b8a7384b7e1618992
|
3 |
+
size 50331648
|
params_shard_126.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:795f480da5b514707722f6fbe61c1a673fe0abe660f5e6ededb1135c69255f80
|
3 |
+
size 100663296
|
params_shard_127.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f32e96798292d13375e6cb5552b9a103e3480711b38abcf2dc7c6766c821c2d
|
3 |
+
size 18874368
|
params_shard_128.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62a0766014a78e224a4b9d4e5b6003fed054026b8323bcab1e5a212cba92fa01
|
3 |
+
size 56623104
|
params_shard_129.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:411a07a5a91c9fdccc790a8c3fff772dcf54e4b03e785143c181ffab2a4a2574
|
3 |
+
size 19273728
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b946c82d0b0f6443fc055c5e003f071e7aeb7cc8b24b5fbd7b7b35aeaa2c011
|
3 |
+
size 18874368
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e309714d37f4b9aa563cc3eab2db1ab37bdafb6794e9d1d8de000d9b0e57b58
|
3 |
+
size 56623104
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4102c4beb346759b4a31ba3354065fd51c33e42fa0b37f0468e7c7425e41ad30
|
3 |
+
size 50331648
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03db7cd6203ddf201640a3e40d882d8018c8a33c2c3f93677dbfae99fbbc2c19
|
3 |
+
size 100663296
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:030014e969aab1f7481055a88259693df5692e1c9915a82dade58b74b44198e8
|
3 |
+
size 18874368
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfa919d46d844ae86da262825c2f198e286d903127bf0d8a01b3717a4fbb4795
|
3 |
+
size 56623104
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0891fb0de46c30c2bcd54f23dc8abf76e2d1ac3e6d580757284c9ea8485441b
|
3 |
+
size 50331648
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30af31bad6d767386c3da1b59187ba23e7d0350e485cfcb5585c5bc2305e7470
|
3 |
+
size 100663296
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:326512b72da0579fa64dc0ce9259ca4f3a410f5f8efe75c2269c0f594de1b64c
|
3 |
+
size 100663296
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b19c200637a7c08a44919b66687e67100c2e76ef192fee8ec2692bdea4c8a3f2
|
3 |
+
size 18874368
|